Watch 3 Star 4 Fork 2

东南大学-王雁刚 / CVPR2020-OOHPythonApache-2.0

Create your Gitee Account
Explore and code with more than 5 million developers,Free private repositories !:)
Sign up
This is the repository of the implemantation of cvpr 2020. spread retract

Clone or download 2.33 KB
Copy Edit Web IDE Raw Blame History

Object-Occluded Human Shape and Pose Estimation from a Single Color Image (CVPR2020 Oral)


This is the offical implentation of 'Object-Occluded Human Shape and Pose Estimation from a Single Color Image' (CVPR2020 Oral). [Project Page]



This code is based on Python 3.7, CUDA 10.0, cuDNN 7.6 on Windows10.

Getting Started

Clone the repo:

git clone

Install the requirements using conda:

conda create -n occlusion python=3.7
conda install pytorch==1.1.0 torchvision==0.3.0 cudatoolkit=10.0 -c pytorch
pip install -r requirements.txt

Running the Demo

First, you need download the trained model from here and put it in trained_model folder. Then, download the official SMPL model and preprocess the neutral model to support pytorch implementation. Finally, put the generated model.pkl in data folder.

To test on your own image, you can edit the cfg_files\demo.yaml and run:

python --config cfg_files\demo.yaml


We provide the 3DOH50K dataset, which is the first real 3D human dataset for the problem of human reconstruction and pose estimation in occlusion scenarios. Visualizing 3DOH50K:

python utils/ --base_dir /PATH/TO/THE/3DOH50K


  title = {Object-Occluded Human Shape and Pose Estimation from a Single Color Image},
  author = {Tianshu, Zhang and Buzhen, Huang and Yangang, Wang},
  booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020}


PyTorch implementation of SMPL model is from CalciferZh.

Comment ( 0 )

Sign in for post a comment